Unsupervised 3D Braided Hair Reconstruction from a Single-View Image
This addresses a domain-specific problem for digital human modeling, offering an incremental improvement over existing hair reconstruction methods.
The paper tackles the problem of reconstructing 3D braided hairstyles from single-view images, which is challenging due to intricate structures, and demonstrates that their unsupervised pipeline outperforms state-of-the-art methods in accuracy, realism, and efficiency.
Reconstructing 3D braided hairstyles from single-view images remains a challenging task due to the intricate interwoven structure and complex topologies of braids. Existing strand-based hair reconstruction methods typically focus on loose hairstyles and often struggle to capture the fine-grained geometry of braided hair. In this paper, we propose a novel unsupervised pipeline for efficiently reconstructing 3D braided hair from single-view RGB images. Leveraging a synthetic braid model inspired by braid theory, our approach effectively captures the complex intertwined structures of braids. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches, providing superior accuracy, realism, and efficiency in reconstructing 3D braided hairstyles, supporting expressive hairstyle modeling in digital humans.